download PDF

Abstract

The article describes an approach to creating a monitoring device of the bearing state, as a node of an asynchronous motor subject to mechanical wear. Under the friction forces, the degradation of bearings proceeds more intensively compared to other electric machine components. The research object is an asynchronous motor of small and medium power up to 200 kW. The choice is due to the comparable cost of the bearing assembly with the electric machine. The registration accuracy of phase current and voltage instantaneous values was achieved by current and voltage sensors on the Hall effect of the compensation type with further digitization on a high-digit analog-to-digital converter. Changes in the bearing technical condition, in terms of degradation of the inner, outer rings or rolling elements, lead to deviation in the current hodograph. This changes both the trajectory and the width. Due to the complex analysis of the hodograph shapes and trajectories, artificial neural network (ANN) classifiers were used. The choice and training of the ANN-classifier was carried out in the course of laboratory studies on the bearing inner ring degradation. The degradation consisted in the artificial wear of the inner ring in the form of shells with different depths and sizes. Before passing the data through the ANN classifier, they were filtered and preprocessed according to the developed algorithm. The article presents an efficient way to enter data into the classifier. The result of the algorithm and method is the achieved 99% convergence and 98% accuracy on the experimental data.

Keywords

Induction motor, Park vector hodograph, current consumption, bearing defects, ANN classifier.

Nikolai A. Korolev Ph.D. (Engineering), Chief Specialist, Educational Research Center for Digital Technologies, Saint Petersburg Mining University, Saint Petersburg, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0002-0583-9695

Yuriy L. Zhukovski Ph.D. (Engineering), Associate Professor, Educational Research Center for Digital Technologies, Saint Petersburg Mining University, Saint Petersburg, Russia, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0003-0312-0019

Natalia I. Koteleva Ph.D. (Engineering), Associate Professor, Department of Technological Processes and Production Automation, Saint Petersburg Mining University, This email address is being protected from spambots. You need JavaScript enabled to view it., https://orcid.org/0000-0002-5970-4534

  1. Vasilyeva N.V., Boikov A.V., Erokhina O.O., Trifonov A.Y. Automated digitization of radial charts. Zapiski Gornogo instituta [Journal of Mining Institute], 2021, vol. 247, pp. 82–87. doi: 10.31897/pmi.2021.1.9. (In Russian)
  2. Safina E., Khokhlov S. Paradox of alternative energy con-sumption: Lean or profligacy? International Journal for Quality Research. 2017, vol. 11(4), pp. 903–916. doi: 10.18421/IJQR11.04-11
  3. Litvinenko V. Digital Economy as a Factor in the Techno-logical Development of the Mineral Sector. Natural Resources Research, 2020, vol. 29(3), pp. 1521-1541. doi: 10.1007/s11053-019-09568-4
  4. Abramovich B.N., Veprikov A.A., Sychev Y.A., Lyakh D.A. Use of active power transducers in industrial DC power sys-tems supplying electrolysis cells. Tsvetnye Met, 2020, vol. 2, pp. 95-100. doi: 10.17580/tsm.2020.02.13
  5. Sychev Y., Zimin R. Improving the quality of electricity in the power supply systems of the mineral resource complex with hybrid filter-compensating devices. Zapiski Gornogo instituta [Journal of Mining Institute], 2021, vol. 247, pp. 132–140. doi: 10.31897/pmi.2021.1.14 (In Russian)
  6. Filatova I., Nikolaichuk L., Zakaev D., Ilin I. Public-Private Partnership as a Tool of Sustainable Development in the Oil-Refining Sector: Russian Case. Sustainability, 2021, vol. 13(9), pp. 5153. doi: 10.3390/su13095153
  7. Belsky A.A., Dobush V., Haikal S.F. Operation of a Single-phase Autonomous Inverter as a Part of a Low-power Wind Complex. Journal of Mining Institute, 2019, vol. 239, pp. 564–569. doi: 10.31897/pmi.2019.5.564
  8. Kulkarni A., Terpenny J., Prabhu V. Sensor Selection Framework for Designing Fault Diagnostics System. Sensors, 2021, vol. 21(19), pp. 6470. doi: 10.3390/s21196470
  9. Kalista K., Liska J., Jakl J. A Vibration Sensor-Based Method for Generating the Precise Rotor Orbit Shape with General Notch Filter Method for New Rotor Seal Design Testing and Diagnostics. Sensors, 2021, vol. 21(15), pp. 5249. doi: 10.3390/s21155249
  10. Hsu J. Monitoring of defects in induction motors through air-gap torque observation. IEEE Transactions on Industry Ap-plications, 1995, vol. 31(5), pp. 1016-1021. doi: 10.1109/28.464514
  11. Bessous N., Zouzou S.E., Bentrah W., Sbaa S., Sahraoui M. Diagnosis of bearing defects in induction motors using dis-crete wavelet transform. International Journal of System As-surance Engineering and Management, 2018, vol. 9(2), pp. 335-343. doi: 10.1007/s13198-016-0459-6 
  12. Gundewar S.K., Kane P.V. Condition Monitoring and Fault Diagnosis of Induction Motor in Electric Vehicle. Machines, Mechanism and Robotics. Springer, 2022, pp. 531-537. doi: 10.1007/978-981-16-0550-5_53
  13. Ewert P., Kowalski C.T., Orlowska-Kowalska T. Low-Cost Monitoring and Diagnosis System for Rolling Bearing Faults of the Induction Motor Based on Neural Network Approach. Electronics, 2020, vol. 9(9), pp. 1334. doi: 10.3390/electronics9091334
  14. Lo N.G., Soualhi A., Frini M., Razik H. Gear and bearings fault detection using motor current signature analysis. 2018 13th IEEE Conference on Industrial Electronics and Appli-cations (ICIEA). IEEE, 2018, pp. 900-905. doi: 10.1109/ICIEA.2018.8397840
  15. Sunder M.; Abishek R.; Sabarivelan S., Maiti M., Bingi K. Bearing Fault Detection in Induction Motors Using Line Currents. ECTI Transactions on Electrical Engineering, Electronics, and Communications, 2021, vol. 19(2), pp. 209–219. doi: 10.37936/ecti-eec.2021192.244163 
  16. Bouchikhi E.H., Choqueuse V., Amirat Y., Benbouzid M.E.H., Turri S. An Efficient Hilbert–Huang Transform-Based Bearing Faults Detection in Induction Machines. IEEE Transactions on Energy Conversion, 2017, vol. 32(2). pp. 401-413. doi: 10.1109/tec.2017.2661541 
  17. Kompella K.D., Rao M.V.G., Rao R.S. Bearing fault detec-tion in a 3 phase induction motor using stator current fre-quency spectral subtraction with various wavelet decomposi-tion techniques. Ain Shams Engineering Journal, 2018, vol. 9(4), pp. 2427-2439. doi: 10.1016/j.asej.2017.06.002 
  18. Fournier E., Picot A., Regnier J., Yamdeu M.T., Andrejak J.-M., Maussion P. Current-Based Detection of Mechanical Unbalance in an Induction Machine Using Spectral Kurtosis with Reference. IEEE Transactions on Industrial Electronics, 2014, vol. 62(3), pp. 1879-1887. doi: 10.1109/tie.2014.2341561 
  19. Gyftakis K.N., Cardoso A.J.M., Antonino-Daviu J.A. Intro-ducing the Filtered Park’s and Filtered Extended Park’s Vec-tor Approach to detect broken rotor bars in induction motors independently from the rotor slots number. Mechanical Sys-tems and Signal Processing, 2017, vol. 93, pp. 30-50. doi: 10.1016/j.ymssp.2017.01.046 
  20. Cruz MA. Marques Cardoso A.J. Rotor Cage Fault Diagnosis in Three-Phase Induction Motors by Extended Park’s Vector Approach. Electric Machines &Power Systems, 2000, vol. 28(4), pp. 289-299. doi: 10.1080/073135600268261 
  21. Silva J., Cardoso A. Bearing failures diagnosis in three-phase induction motors by extended Park’s vector approach. 31st Annual Conference of IEEE Industrial Electronics Society. IEEE, 2005, pp. 2591–2596. doi: 10.1109/IECON.2005.1569315 
  22. Caseiro J.A.A., Mendes A.M.S., Cardoso A.J.M. Fault diag-nosis on a PWM rectifier AC drive system with fault toler-ance using the average current Park's vector approach. 2009 IEEE International Electric Machines and Drives Conference. IEEE, 2009, pp. 695-701. doi: 10.1109/iemdc.2009.5075281 
  23. Curreri F., Patanè L., Xibilia M.G. Soft Sensor Transferabil-ity: A Survey. Applied Sciences, 2021, vol. 11(16), pp. 7710. doi: 10.3390/app11167710 
  24. Dybkowski M., Klimkowski K. Artificial Neural Network Application for Current Sensors Fault Detection in the Vector Controlled Induction Motor Drive. Sensors, 2019, vol. 19(3), pp. 571. doi: 10.3390/s19030571 
  25. Zhou X., Mao S., Li M. A Novel Anti-Noise Fault Diagnosis Approach for Rolling Bearings Based on Convolutional Neural Network Fusing Frequency Domain Feature Matching Algorithm. Sensors, 2021, vol. 21(16), pp. 5532. doi: 10.3390/s21165532 
  26. Mendes A.M.S., Cardoso A.J.M. Voltage source inverter fault diagnosis in variable speed AC drives, by the average current Park's vector approach. IEEE International Electric Machines and Drives Conference. IEEE, 1999, pp. 704-706. doi: 10.1109/iemdc.1999.769220 
  27. Muñoz-Aguilar R.-S., Rodriguez P., Dòria-Cerezo A., Can-dela I., Luna A. A sensor-less sliding mode control scheme for a stand-alone wound rotor synchronous generator under unbalanced load conditions. International Journal of Electrical Power & Energy Systems, 2014, vol. 60, pp. 275-282. doi: 10.1016/j.ijepes.2014.03.003 
  28. Cornell E.P., Lipo T.A. Modeling and Design of Controlled Current Induction Motor Drive Systems. IEEE Transactions on Industry Applications, 1977, vol. 4, pp. 321-330. doi: 10.1109/tia.1977.4503414 
  29. Thomson W., Fenger M. Current signature analysis to detect induction motor faults. IEEE Industry Applications Magazine, 2001, vol. 7(4), pp. 26-34. doi: 10.1109/2943.930988 
  30. Fenger M., LLoyd B.A., Thomson W.T. Development of a tool to detect faults in induction motors via current signature analysis In Proceedings of the 2003 IEEE-IAS/PCA Cement Industry Conference. IEEE, 2003, pp. 37-46. doi: 2003-05-04/09 
  31. Khanaki R., MohdRadzi M.A., Marhaban M.H. Artificial neural network based maximum power point tracking con-troller for photovoltaic standalone system. International Journal of Green Energy, 2016, vol. 13(3), pp. 283-291. doi: 10.1007/s00500-021-05653-0 
  32. Muruganandam M., Madheswaran M. Stability analysis and implementation of chopper fed DC series motor with hybrid PID-ANN controller. International Journal of Control, Au-tomation and Systems, 2013, vol. 11(5), pp. 966-975. doi: 10.1007/s12555-012-9209-y 
  33. Sancho-Asensio A., Orriols-Puig A., Golobardes Robust E. Robust on-line neural learning classifier system for data stream classification tasks. Soft Computing, 2014, vol. 18(8), 1441-1461. doi: 10.1007/s00500-014-1233-9 
  34. Liu L., Özsu M.T. In Encyclopedia of Database Systems. Springer Singapore, 2009. 765 p. doi: 10.1007/978-1-4614-8265-9 
  35. Evgeniou T., Pontil M. Support vector machines: Theory and applications. Advanced Course on Artificial Intelligence. Springer, 1999, pp. 249-257. doi: 10.1007/3-540-44673-7_12 
  36. Cunningham P. Delany S.J. k-Nearest neighbour classifiers-A Tutorial. ACM Computing Surveys (CSUR), 2021, vol. 54(6),pp. 1-25. doi: 10.1145/3459665 
  37. Bichurin M., Petrov R., Leontiev V., Semenov G., Sokolov O. Magnetoelectric current sensors. Sensors, 2017, vol. 17(6), pp. 1271. doi: 10.3390/s17061271

Korolev N.A., Zhukovski Yu.L., Koteleva N.I. Bearing State Monitoring Device for an Asynchronous Motor by the Current and Voltage Park Vector Components. Elektrotekhnicheskie sistemy i kompleksy [Electrotechnical Systems and Complexes], 2022, no. 2(55), pp. 62-70. (In Russian). https://doi.org/10.18503/2311-8318-2022-2(55)-62-70